Interspeech 2022

1,122 papers
Interspeech 2022 featured research focused on end-to-end learning from raw audio waveforms and improving robust speech processing in out-of-distribution environments. Technical developments emphasized architectural innovations, such as asymmetric convolutions for time-frequency processing and the integration of local and global contexts. Multi-resolution architectures and precise temporal grounding for sound event detection were also prominent themes during this edition. The year's contributions addressed diverse applications, including the automatic detection of speech sound disorders in children and privacy-preserving techniques for automatic speech recognition using self-supervised learning. Research also explored speaker identification challenges, such as mitigating within-household confusability through graph-based multi-view fusion. Other work included advancements in speech enhancement via cross-layer similarity knowledge distillation and any-to-any voice conversion using contrastive predictive coding frameworks. Prolific contributors to this edition included researchers such as Chi-Chun Lee, Yu Tsao, and Hsin-Min Wang.

Top Research Directions

Research directions most represented by Interspeech 2022 papers.

Learning High-Level Acoustic Structures from Unlabeled Audio 41
Overcoming Data Scarcity in Low-Resource Speech Recognition 28
Integrating Local and Global Context in Speech Architectures 27
Balancing Latency and Accuracy in Streaming Speech Recognition 25
Partitioning Variance with Linear Mixed Effects Models 21
Generalization to Unseen Acoustic Environments 20
Zero Shot Speaker Generalization for Speech Synthesis 20
The Perceptual Evaluation Gap in Generative Audio 20
Joint Optimization of Speech Enhancement and Recognition 18
Fine-Grained Prosodic Control for Expressive Speech Synthesis 18
The Single Speaker Generalization Bottleneck in Speech Synthesis 18
Complex Spectral Mapping for Phase Aware Signal Reconstruction 17
Robust Natural Language Understanding for Noisy Speech Transcripts 17
Resolving Overlapping Speech in Multi-Speaker Audio 17
Parameter Efficient Speech and Audio Processing 16

Top Authors

AuthorPapers
Shinji Watanabe23
Helen M. Meng14
Hung-yi Lee10
Zhiyong Wu10
Joon-Hyuk Chang9
Yanmin Qian9
Yonghong Yan9
Haizhou Li8
Jinyu Li8
Longbiao Wang8
Jing Xiao7
Lei Xie7
Yu Tsao7
Alan Black6
Jesus Villalba6
Joseph Keshet6
Jun Du6
Michael Auli6
Najim Dehak6
Yu Wu6

Impactful Papers

Papers from Interspeech 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Unsupervised Symbolic Music Segmentation using Ensemble Temporal Prediction Errors
Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition
Unsupervised Training of Sequential Neural Beamformer Using Coarsely-separated and Non-separated Signals
Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction
Unsupervised Voice Activity Detection by Modeling Source and System Information using Zero Frequency Filtering
Unsupervised Word Segmentation using K Nearest Neighbors
Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models
Use of Nods Less Synchronized with Turn-Taking and Prosody During Conversations in Adults with Autism
Use of prosodic and lexical cues for disambiguating wh-words in Korean
User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition on Federated Learning
UserLibri: A Dataset for ASR Personalization Using Only Text
Using cross-model learnings for the Gram Vaani ASR Challenge 2022
Using Data Augmentation and Consistency Regularization to Improve Semi-supervised Speech Recognition
Using Fluency Representation Learned from Sequential Raw Features for Improving Non-native Fluency Scoring
Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
Utterance-by-utterance overlap-aware neural diarization with Graph-PIT
Vaccinating SER to Neutralize Adversarial Attacks with Self-Supervised Augmentation Strategy
VAgyojaka: An Annotating and Post-Editing Tool for Automatic Speech Recognition
Validation of the Neuro-Concept Detector framework for the characterization of speech disorders: A comparative study including Dysarthria and Dysphonia
Variability in Production of Non-Sibilant Fricative [ç] in /hi/
Variations of multi-task learning for spoken language assessment
VCSE: Time-Domain Visual-Contextual Speaker Extraction Network
Vector-quantized Variational Autoencoder for Phase-aware Speech Enhancement
Vietnamese Capitalization and Punctuation Recovery Models
View-Specific Assessment of L2 Spoken English
Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition
Visualising Model Training via Vowel Space for Text-To-Speech Systems
Visually-aware Acoustic Event Detection using Heterogeneous Graphs
Vocal effort modeling in neural TTS for improving the intelligibility of synthetic speech in noise
VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices
Vocal-Tract Area Functions with Articulatory Reality for Tract Opening
Voice2Alliance: Automatic Speaker Diarization and Quality Assurance of Conversational Alignment
Voice Activity Projection: Self-supervised Learning of Turn-taking Events
Voice Conversion Can Improve ASR in Very Low-Resource Settings
VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration
VoiceLab: Software for Fully Reproducible Automated Voice Analysis
VoiceMe: Personalized voice generation in TTS
Voice Puppetry with FastPitch
Voicing decision based on phonemes classification and spectral moments for whisper-to-speech conversion
Voicing neutralization in Romanian fricatives across different speech styles
VOT and F0 perturbations for the realization of voicing contrast in Tohoku Japanese
VQ-T: RNN Transducers using Vector-Quantized Prediction Network States
VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature
W2V2-Light: A Lightweight Version of Wav2vec 2.0 for Automatic Speech Recognition
Watch Me Speak: 2D Visualization of Human Mouth during Speech
WA-Transformer: Window Attention-based Transformer with Two-stage Strategy for Multi-task Audio Source Separation
wav2vec2-based Speech Rating System for Children with Speech Sound Disorder
Wav2Vec-Aug: Improved self-supervised training with limited data
Wav2vec behind the Scenes: How end2end Models learn Phonetics

« prev Page 22/23 next »